![[Toho University]](image/CLogo_Kihon_process.jpg "[Toho University]")
|
ノート/Generationとdeconvolution (2016-08-14)http://pepper.is.sci.toho-u.ac.jp/pepper/index.php?%A5%CE%A1%BC%A5%C8%2FGeneration%A4%C8deconvolution%20%282016-08-14%29 |
![[YYLAB]](image/yamanouc2.png "[YYLAB]")
|
|
|
ノート/Generationとdeconvolution (2016-08-14)http://pepper.is.sci.toho-u.ac.jp/pepper/index.php?%A5%CE%A1%BC%A5%C8%2FGeneration%A4%C8deconvolution%20%282016-08-14%29 |
|
訪問者数 2487 最終更新 2016-08-15 (月) 16:10:58
出典: UNSUPERVISED REPRESENTATION LEARNING WITH DEEP CONVOLUTIONAL GENERATIVE ADVERSARIAL NETWORKS
すぎゃーん(id:sugyan)氏： TensorFlowによるDCGANでアイドルの顔画像生成
分類器などで使っている畳み込みの逆方向の操作で、最初は小さな多数のfeature mapにreshapeして、これを徐々に小数の大きなものにしていく。"deconvolution"と呼んだり呼ばなかったり、なのかな。TensorFlowではこの操作はtf.nn.conv2d_transposeという関数で実現するようだ。
Tensorflowのマニュアルでは conv2d_transpose
本件、deconvolutionは別の意味 （この論文参照：Deconvolutional Networks） でも使われるので、要注意。
それと区別するために、Tensorflowでは、"Rename deconv2d to conv2d_transpose and expose publicly" などと
言っているようだ。
それで、彼のプログラムだと、dcgan.py では、
def __generator(self, depth1, depth2, depth3, depth4):
reuse = False
def model(inputs):
nonlocal reuse
depths = [depth1, depth2, depth3, depth4, 3]
i_depth = depths[0:4]
o_depth = depths[1:5]
with tf.variable_scope('g', reuse=reuse):
# reshape from inputs
with tf.variable_scope('reshape'):
fc = tf.contrib.layers.fully_connected(inputs, i_depth[0] * self.f_size * self.f_size, normalizer_fn=tf.contrib.layers.batch_norm)
out = tf.reshape(fc, [-1, self.f_size, self.f_size, i_depth[0]])
# deconvolution (transpose of convolution) layers
for i in range(4):
with tf.variable_scope('conv%d' % (i + 1)):
activation_fn = tf.nn.relu if i < 3 else None
normalizer_fn = tf.contrib.layers.batch_norm if i < 3 else None
out = tf.contrib.layers.conv2d_transpose(out, o_depth[i], [5, 5], stride=2, activation_fn=activation_fn, normalizer_fn=normalizer_fn)
reuse = True
return tf.nn.tanh(out)
return model
てな感じになっている。
もう１つ、Taehoon Kim氏によるTensorflowでのインプリだと、（改名前のdeconvの名前で使っている）
model.py
Chainer
def discriminator(self, image, y=None, reuse=False):
if reuse:
tf.get_variable_scope().reuse_variables()
if not self.y_dim:
h0 = lrelu(conv2d(image, self.df_dim, name='d_h0_conv'))
h1 = lrelu(self.d_bn1(conv2d(h0, self.df_dim*2, name='d_h1_conv')))
h2 = lrelu(self.d_bn2(conv2d(h1, self.df_dim*4, name='d_h2_conv')))
h3 = lrelu(self.d_bn3(conv2d(h2, self.df_dim*8, name='d_h3_conv')))
h4 = linear(tf.reshape(h3, [self.batch_size, -1]), 1, 'd_h3_lin')
return tf.nn.sigmoid(h4), h4
else:
yb = tf.reshape(y, [self.batch_size, 1, 1, self.y_dim])
x = conv_cond_concat(image, yb)
h0 = lrelu(conv2d(x, self.c_dim + self.y_dim, name='d_h0_conv'))
h0 = conv_cond_concat(h0, yb)
h1 = lrelu(self.d_bn1(conv2d(h0, self.df_dim + self.y_dim, name='d_h1_conv')))
h1 = tf.reshape(h1, [self.batch_size, -1])
h1 = tf.concat(1, [h1, y])
h2 = lrelu(self.d_bn2(linear(h1, self.dfc_dim, 'd_h2_lin')))
h2 = tf.concat(1, [h2, y])
h3 = linear(h2, 1, 'd_h3_lin')
return tf.nn.sigmoid(h3), h3
def generator(self, z, y=None):
if not self.y_dim:
s = self.output_size
s2, s4, s8, s16 = int(s/2), int(s/4), int(s/8), int(s/16)
# project `z` and reshape
self.z_, self.h0_w, self.h0_b = linear(z, self.gf_dim*8*s16*s16, 'g_h0_lin', with_w=True)
self.h0 = tf.reshape(self.z_, [-1, s16, s16, self.gf_dim * 8])
h0 = tf.nn.relu(self.g_bn0(self.h0))
self.h1, self.h1_w, self.h1_b = deconv2d(h0,
[self.batch_size, s8, s8, self.gf_dim*4], name='g_h1', with_w=True)
h1 = tf.nn.relu(self.g_bn1(self.h1))
h2, self.h2_w, self.h2_b = deconv2d(h1,
[self.batch_size, s4, s4, self.gf_dim*2], name='g_h2', with_w=True)
h2 = tf.nn.relu(self.g_bn2(h2))
h3, self.h3_w, self.h3_b = deconv2d(h2,
[self.batch_size, s2, s2, self.gf_dim*1], name='g_h3', with_w=True)
h3 = tf.nn.relu(self.g_bn3(h3))
h4, self.h4_w, self.h4_b = deconv2d(h3,
[self.batch_size, s, s, self.c_dim], name='g_h4', with_w=True)
return tf.nn.tanh(h4)
else:
s = self.output_size
s2, s4 = int(s/2), int(s/4)
# yb = tf.expand_dims(tf.expand_dims(y, 1),2)
yb = tf.reshape(y, [self.batch_size, 1, 1, self.y_dim])
z = tf.concat(1, [z, y])
h0 = tf.nn.relu(self.g_bn0(linear(z, self.gfc_dim, 'g_h0_lin')))
h0 = tf.concat(1, [h0, y])
h1 = tf.nn.relu(self.g_bn1(linear(z, self.gf_dim*2*s4*s4, 'g_h1_lin')))
h1 = tf.reshape(h1, [self.batch_size, s4, s4, self.gf_dim * 2])
h1 = conv_cond_concat(h1, yb)
h2 = tf.nn.relu(self.g_bn2(deconv2d(h1, [self.batch_size, s2, s2, self.gf_dim * 2], name='g_h2')))
h2 = conv_cond_concat(h2, yb)
return tf.nn.sigmoid(deconv2d(h2, [self.batch_size, s, s, self.c_dim], name='g_h3'))
Rezoolab氏によるChainerのインプリ 出典は Chainerを使ってコンピュータにイラストを描かせる の下の方。
class Generator(chainer.Chain):
n_hidden = 100
sigma = 0.01
def __init__(self):
super(Generator, self).__init__(
fc5=L.Linear(100, 512 * 4 * 4),
norm5=L.BatchNormalization(512 * 4 * 4),
conv4=L.Deconvolution2D(512, 256, ksize=4, stride=2, pad=1),
norm4=L.BatchNormalization(256),
conv3=L.Deconvolution2D(256, 128, ksize=4, stride=2, pad=1),
norm3=L.BatchNormalization(128),
conv2=L.Deconvolution2D(128, 64, ksize=4, stride=2, pad=1),
norm2=L.BatchNormalization(64),
conv1=L.Deconvolution2D(64, 3, ksize=4, stride=2, pad=1))
init_normal(
[self.conv1, self.conv2, self.conv3,
self.conv4, self.fc5], self.sigma)
def __call__(self, z, train=True):
n_sample = z.data.shape[0]
test = not train
h = F.relu(self.norm5(self.fc5(z), test=test))
h = F.reshape(h, (n_sample, 512, 4, 4))
h = F.relu(self.norm4(self.conv4(h), test=test))
h = F.relu(self.norm3(self.conv3(h), test=test))
h = F.relu(self.norm2(self.conv2(h), test=test))
x = F.tanh(self.conv1(h))
return x
def make_optimizer(self):
return chainer.optimizers.Adam(alpha=1e-4, beta1=0.5)
def generate_hidden_variables(self, n):
return np.asarray(
np.random.uniform(
low=-1.0, high=1.0, size=(n, self.n_hidden)),
dtype=np.float32)
Maccha氏によるChainerのインプリ Chainerで顔イラストの自動生成
コードの出典は GDCGAN.py
class Generator(chainer.Chain):
def __init__(self):
super(Generator, self).__init__(
l0z = L.Linear(nz, 6*6*512, wscale=0.02*math.sqrt(nz)),
dc1 = L.Deconvolution2D(512, 256, 4, stride=2, pad=1, wscale=0.02*math.sqrt(4*4*512)),
dc2 = L.Deconvolution2D(256, 128, 4, stride=2, pad=1, wscale=0.02*math.sqrt(4*4*256)),
dc3 = L.Deconvolution2D(128, 64, 4, stride=2, pad=1, wscale=0.02*math.sqrt(4*4*128)),
dc4 = L.Deconvolution2D(64, 3, 4, stride=2, pad=1, wscale=0.02*math.sqrt(4*4*64)),
bn0l = L.BatchNormalization(6*6*512),
bn0 = L.BatchNormalization(512),
bn1 = L.BatchNormalization(256),
bn2 = L.BatchNormalization(128),
bn3 = L.BatchNormalization(64),
)
def __call__(self, z, test=False):
h = F.reshape(F.relu(self.bn0l(self.l0z(z), test=test)), (z.data.shape[0], 512, 6, 6))
h = F.relu(self.bn1(self.dc1(h), test=test))
h = F.relu(self.bn2(self.dc2(h), test=test))
h = F.relu(self.bn3(self.dc3(h), test=test))
x = (self.dc4(h))
return x
Chainerマニュアルでは、
This link wraps the deconvolution_2d() function and holds the filter weight and bias vector as parameters.
This is an implementation of two-dimensional deconvolution.
def forward_cpu(self, inputs):
x, W = inputs[:2]
b = inputs[2] if len(inputs) == 3 else None
kh, kw = W.shape[2:]
_, _, h, w = x.shape
gcol = numpy.tensordot(W, x, (0, 1)).astype(x.dtype, copy=False)
# - k, m, n: shape of out_channel
# - b: number of inputs
# - h, w: height and width of kernels
# k, m, n, b, h, w -> b, k, m, n, h, w
gcol = numpy.rollaxis(gcol, 3)
if self.outh is None:
self.outh = conv.get_deconv_outsize(h, kh, self.sy, self.ph)
if self.outw is None:
self.outw = conv.get_deconv_outsize(w, kw, self.sx, self.pw)
y = conv.col2im_cpu(
gcol, self.sy, self.sx, self.ph, self.pw, self.outh, self.outw)
# b, k, h, w
if b is not None:
y += b.reshape(1, b.size, 1, 1)
return y,def get_conv_outsize(size, k, s, p, cover_all=False):
if cover_all:
return (size + p * 2 - k + s - 1) // s + 1
else:
return (size + p * 2 - k) // s + 1
def get_deconv_outsize(size, k, s, p, cover_all=False):
if cover_all:
return s * (size - 1) + k - s + 1 - 2 * p
else:
return s * (size - 1) + k - 2 * p
となっている。
DCGAN-Generator.png